[ovs-dev] Improved Packet Drop Statistics in OVS

Hi, Currently we are working on improving the packet drop statistics in OVS. Following link contains details of our proposal to improve packet drop statistics in OVS. https://docs.google.com/document/d/1EtntZ8tPYr8lnbWyM385XMO8NIZ7v-RqBD1oPqLInb4/edit?usp=sharing We would like to get your comm

Re: [ovs-dev] [PATCH v1] netdev-dpdk: Execute QoS Checking before copying to mbuf

ping... Comments are welcome. Thanks Zhenyu Gao 2017-08-18 9:28 GMT+08:00 Gao Zhenyu : > Hi Ian, > >This patch is pending for a long time. May I know if I should revise it? > > > Thanks > Zhenyu Gao > > 2017-08-08 17:34 GMT+08:00 Gao Zhenyu : > >> Thanks for the review. Please let me know i

Re: [ovs-dev] [PATCH v3 1/2] ovn-controller: readonly mode binding_run and get_br_int

On Tue, Aug 8, 2017 at 1:01 PM, Ben Pfaff wrote: > > On Thu, Jul 13, 2017 at 03:54:01PM -0700, Han Zhou wrote: > > This change is to prepare for the future change for multi-threading. > > Both binding_run() and get_br_int() are needed by pinctrl thread, > > but we don't want to update SB DB or cre

[ovs-dev] [PATCH v4 3/3] ovn-controller: Use separate thread for packet-in processing.

This patch introduces multi-threading for ovn-controller and use dedicated thread for packet-in processing as a start. It decouples packet-in processing and ovs flow computing, so that packet-in inputs won't trigger flow recomputing, and flow computing won't block packet-in processing. In large sca

[ovs-dev] [PATCH v4 2/3] ovn-controller: Move ovnsb cursors to idl context.

Cursors need to be bound with idl so that different idl for same DB can work properly without stepping onto each other. This will be needed for a future patch that requires separate ovnsb idl for different thread. Signed-off-by: Han Zhou --- v3->v4: this change was not in v3. It is needed because

[ovs-dev] [PATCH v4 1/3] ovn-controller: readonly mode binding_run and get_br_int

This change is to prepare for the future change for multi-threading. Both binding_run() and get_br_int() are needed by pinctrl thread, but we don't want to update SB DB or create bridges in that scenario, so need "readonly" mode for these functions. Signed-off-by: Han Zhou Co-authored-by: Ben Pfa

Re: [ovs-dev] [PATCH] fix ovsdb-server memory growth issues when ovs-vsctl cmd stucking.

In our environment when applied this patch can solve this problem. For the root cause we are still analyzing, can you help us? Through our analysis, we suspect that when the ovs-vsctl cmd (ex: ovs-vsctl list interface) sticking, but unix socket link still exists. At this time if the ovsdb data u